Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Contact information/addresses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     annoyed
    -0.07
     conservative
    -0.07
    オ
    -0.07
     weird
    -0.06
     woman
    -0.06
     oddly
    -0.06
    礼
    -0.06
     BOOT
    -0.06
     annoy
    -0.06
    の子
    -0.06
    POSITIVE LOGITS
    .Imp
    0.06
    curacy
    0.06
     volunte
    0.06
     spp
    0.06
    dsp
    0.06
     interdisciplinary
    0.06
    ,long
    0.06
     Pv
    0.06
     lbs
    0.06
     Transitional
    0.06
    Act Density 0.023%

    No Known Activations